type_text

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With zero annotations, the description must carry the full behavioral load, and it does contribute two real facts: submit=True presses Enter, and passwords are off-limits. But it omits whether the existing field contents are cleared, whether the element is focused, what happens on a bad ref/selector, and the confirmation/auth implications of pressing Enter - significant gaps for an interactive mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two compact clauses with no filler, and the primary behavior is front-loaded ahead of the caveat. It is arguably too terse for a four-parameter interactive tool, but nothing present is redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and the description covers the core action plus the Enter behavior. Against 0% schema coverage and no annotations, however, the targeting contract between `ref` and `selector` remains underspecified for an agent that must choose between them on first call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description is the only source of parameter meaning. It usefully explains that `ref` and `selector` are alternative ways to target the field and that `submit` triggers Enter, but it never states precedence when both are supplied, whether at least one is required, or that `text` is inserted verbatim.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete action and target: 'Fill a field by ref or selector' tells an agent it types text into a located element, distinguishing it from press_key and click in the sibling list. It doesn't explicitly say it types the `text` argument, but the pairing of name and description makes the intent unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Never use it for passwords' is a genuine when-not exclusion, but it is the only one and no alternative is named (login_begin/login_finish are plausible redirects that go unmentioned). The positive trigger - fill a form field - is implied by 'Fill a field' rather than stated as guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.